app.py

import os
import gradio as gr
import cv2
from ultralytics import YOLO

# Define the folder containing the images and video
folder_path = "info"  # Replace with your folder name or path

# Get list of files from the folder
image_files = [os.path.join(folder_path, f) for f in os.listdir(folder_path) if f.lower().endswith(('.jpg', '.jpeg', '.png'))]
video_files = [os.path.join(folder_path, f) for f in os.listdir(folder_path) if f.lower().endswith(('.mp4', '.avi', '.mov'))]

# Ensure the folder contains the expected number of files
if len(image_files) < 2 or len(video_files) < 1:
    raise ValueError("Folder must contain at least 2 images and 1 video.")

# Select the first two images and the first video
image_examples = [[image_files[0]], [image_files[1]]]
video_examples = [[video_files[0]]]

# Load the YOLO model
model = YOLO('best.pt')

# Function for processing images
def show_preds_image(image_path):
    image = cv2.imread(image_path)
    results = model.predict(source=image_path)
    annotated_image = results[0].plot()
    return cv2.cvtColor(annotated_image, cv2.COLOR_BGR2RGB)

# Function for processing videos
def show_preds_video(video_path):
    cap = cv2.VideoCapture(video_path)
    out_frames = []
    fps = int(cap.get(cv2.CAP_PROP_FPS))
    while cap.isOpened():
        ret, frame = cap.read()
        if not ret:
            break
        results = model.predict(source=frame)
        annotated_frame = results[0].plot()
        out_frames.append(cv2.cvtColor(annotated_frame, cv2.COLOR_BGR2RGB))
    cap.release()

    # Save the annotated video
    output_path = "annotated_video.mp4"
    height, width, _ = out_frames[0].shape
    fourcc = cv2.VideoWriter_fourcc(*"mp4v")
    writer = cv2.VideoWriter(output_path, fourcc, fps, (width, height))
    for frame in out_frames:
        writer.write(cv2.cvtColor(frame, cv2.COLOR_RGB2BGR))
    writer.release()
    return output_path

# Gradio interfaces
inputs_image = gr.Image(type="filepath", label="Input Image")
outputs_image = gr.Image(type="numpy", label="Output Image")
interface_image = gr.Interface(
    fn=show_preds_image,
    inputs=inputs_image,
    outputs=outputs_image,
    title="Safety Head Detector - Image",
    examples=image_examples,
)

inputs_video = gr.Video(label="Input Video")
outputs_video = gr.Video(label="Annotated Output")
interface_video = gr.Interface(
    fn=show_preds_video,
    inputs=inputs_video,
    outputs=outputs_video,
    title="Safety Head Detector - Video",
    examples=video_examples,
)

# Combine into a tabbed interface
gr.TabbedInterface(
    [interface_image, interface_video],
    tab_names=['Image Inference', 'Video Inference']
).launch(share=True)